<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
neuroscience-to-dev-bio-6
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0272
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
20.2304 | 0.92 | 8 | 17.4919 |
18.2683 | 1.92 | 16 | 15.5664 |
14.7103 | 2.92 | 24 | 12.5939 |
13.0748 | 3.92 | 32 | 11.1345 |
12.0191 | 4.92 | 40 | 10.0448 |
10.7466 | 5.92 | 48 | 8.4701 |
8.9879 | 6.92 | 56 | 6.3367 |
7.3434 | 7.92 | 64 | 5.3961 |
6.4423 | 8.92 | 72 | 4.7649 |
5.735 | 9.92 | 80 | 4.1861 |
5.0266 | 10.92 | 88 | 3.5610 |
4.2148 | 11.92 | 96 | 2.8360 |
3.2942 | 12.92 | 104 | 2.0238 |
2.2981 | 13.92 | 112 | 1.2176 |
1.3502 | 14.92 | 120 | 0.6073 |
0.6497 | 15.92 | 128 | 0.2784 |
0.2704 | 16.92 | 136 | 0.1443 |
0.1185 | 17.92 | 144 | 0.0861 |
0.0628 | 18.92 | 152 | 0.0524 |
0.0346 | 19.92 | 160 | 0.0411 |
0.0226 | 20.92 | 168 | 0.0333 |
0.0168 | 21.92 | 176 | 0.0333 |
0.0155 | 22.92 | 184 | 0.0297 |
0.0127 | 23.92 | 192 | 0.0340 |
0.0147 | 24.92 | 200 | 0.0331 |
0.0116 | 25.92 | 208 | 0.0328 |
0.0104 | 26.92 | 216 | 0.0265 |
0.0167 | 27.92 | 224 | 0.0276 |
0.0175 | 28.92 | 232 | 0.0270 |
0.014 | 29.92 | 240 | 0.0295 |
0.011 | 30.92 | 248 | 0.0287 |
0.0094 | 31.92 | 256 | 0.0303 |
0.008 | 32.92 | 264 | 0.0301 |
0.0074 | 33.92 | 272 | 0.0289 |
0.0063 | 34.92 | 280 | 0.0272 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2